© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74032
    Prev
    Next
    INDEX
    Explanations

    speaker's location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    1
    -2.48
    -
    -2.11
     begeistert
    -1.97
     äußerst
    -1.84
     beeindruck
    -1.84
     durchaus
    -1.80
     Recuperado
    -1.77
     शुर
    -1.74
     faszin
    -1.73
     mildly
    -1.73
    POSITIVE LOGITS
    燐
    1.98
    tığı
    1.96
    ”？
    1.84
     feit
    1.84
    farer
    1.83
    摀
    1.80
     în
    1.80
    ⬈
    1.79
    en
    1.74
    dienne
    1.73
    Activations Density 0.004%

    No Known Activations